save-model-final
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on the jbarat/plant_species dataset. It achieves the following results on the evaluation set:
- Loss: 0.3658
- Accuracy: 0.875
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0003
- train_batch_size: 64
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 10 | 1.0202 | 0.675 |
| No log | 2.0 | 20 | 0.7625 | 0.7375 |
| No log | 3.0 | 30 | 0.5602 | 0.8625 |
| No log | 4.0 | 40 | 0.5282 | 0.825 |
| No log | 5.0 | 50 | 0.8285 | 0.7875 |
| No log | 6.0 | 60 | 0.6724 | 0.825 |
| No log | 7.0 | 70 | 0.7429 | 0.8125 |
| No log | 8.0 | 80 | 0.9518 | 0.8125 |
| No log | 9.0 | 90 | 0.8012 | 0.8125 |
| 0.2718 | 10.0 | 100 | 0.8500 | 0.8125 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2